Legal claims defining the scope of protection. Each claim is shown in both the original legal language and a plain English translation.
1. A distributed analytics computer system to control the operation of a plurality of monitored systems, comprising: an architect subsystem and an edge subsystem, said edge subsystem comprising a plurality of edge processing devices to be located proximate to said plurality of monitored systems, wherein: said architect subsystem is operable to deploy analytic models to said edge processing devices based on sensor characteristics of said monitored systems; and, each of said edge processing devices is operable to: 1) receive at least one of said analytic models and independently perform predictive and prescriptive analytics on sensor data from at least one monitored system, wherein said prescriptive analytics includes a future action on a component of said monitored system associated with said sensor; 2) provide control signals to said at least one monitored system according to said predictive and prescriptive analytics; and, 3) periodically send information to said architect subsystem, including monitored system responses to said control signals, whereby said architect subsystem can modify said analytic models to improve system performance of said monitored systems.
A distributed analytics computer system monitors and controls multiple systems by deploying predictive and prescriptive analytics at the edge. The system includes an architect subsystem and an edge subsystem. The edge subsystem consists of multiple edge processing devices placed near the monitored systems. The architect subsystem deploys analytic models to these edge devices based on sensor characteristics of the monitored systems. Each edge device independently performs predictive and prescriptive analytics on sensor data from its associated monitored system. The prescriptive analytics determine future actions for system components. The edge devices then send control signals to the monitored systems based on these analytics. Additionally, the edge devices periodically transmit information back to the architect subsystem, including system responses to the control signals. The architect subsystem uses this feedback to refine and improve the analytic models, enhancing overall system performance. This approach enables real-time decision-making at the edge while allowing centralized optimization of the analytics models.
2. The distributed analytics system as recited in claim 1 , wherein said edge subsystem is configured to perform said predictive and prescriptive analytics on at least a component of said at least one monitored system based on said sensor data.
This invention relates to distributed analytics systems designed to process and analyze sensor data from monitored systems, particularly in edge computing environments. The system addresses the challenge of efficiently performing predictive and prescriptive analytics on sensor data collected from industrial or operational systems, such as machinery, infrastructure, or environmental monitoring devices. By processing data at the edge, the system reduces latency and bandwidth requirements compared to cloud-based analytics, enabling real-time decision-making and automated corrective actions. The system includes an edge subsystem that interfaces with one or more monitored systems equipped with sensors. The edge subsystem is configured to perform predictive analytics, such as forecasting system performance or failure risks, and prescriptive analytics, such as recommending maintenance actions or operational adjustments. The analytics are applied to specific components of the monitored systems based on the sensor data, allowing for targeted insights and interventions. The edge subsystem may also preprocess or filter data before transmitting it to a central analytics platform, optimizing resource usage and improving scalability. The system leverages distributed computing to balance workloads between edge and cloud resources, ensuring efficient data processing while maintaining low-latency responsiveness. This approach is particularly useful in environments where immediate actions are required, such as industrial automation, smart cities, or predictive maintenance applications. The invention enhances operational efficiency, reduces downtime, and improves decision-making by integrating real-time analytics at the edge of the network.
3. The distributed analytics system as recited in claim 1 , wherein said information includes a current status of a component of said at least one monitored system associated with said sensor.
A distributed analytics system monitors and analyzes data from sensors associated with one or more systems. The system collects sensor data and processes it to extract meaningful information, such as the current status of a component within the monitored system. This information is then used to support decision-making, optimize performance, or detect anomalies. The system may include multiple nodes or devices that collaborate to process and analyze the data, ensuring scalability and reliability. By continuously monitoring the status of system components, the analytics system enables real-time insights and proactive maintenance, reducing downtime and improving operational efficiency. The system may also integrate with other data sources or external systems to provide a comprehensive view of the monitored environment. The analytics capabilities may include statistical analysis, pattern recognition, predictive modeling, or other techniques to derive actionable insights from the sensor data. The system is designed to handle large volumes of data efficiently, ensuring timely and accurate analysis.
4. The distributed analytics system as recited in claim 1 , wherein said information includes a characteristic of said at least one monitored system based on said sensor data from a plurality of sensors.
A distributed analytics system monitors and analyzes data from multiple sensors to extract characteristics of one or more monitored systems. The system collects sensor data from various sources, processes the data in a distributed manner, and derives meaningful insights or characteristics about the monitored systems. These characteristics may include performance metrics, operational states, or other derived attributes that describe the behavior or condition of the monitored systems. The distributed architecture allows for scalable and efficient processing of large volumes of sensor data, enabling real-time or near-real-time analysis. The system may be applied in industrial automation, environmental monitoring, healthcare, or other domains where sensor-based data analysis is required. By aggregating and analyzing data from multiple sensors, the system provides a comprehensive understanding of the monitored systems, facilitating better decision-making and predictive maintenance. The distributed nature of the system ensures robustness, fault tolerance, and the ability to handle diverse data sources and processing requirements.
5. The distributed analytics system as recited in claim 1 , wherein said predictive analytics includes an estimate of an operation of a component of said at least one monitored system associated with said sensor.
A distributed analytics system monitors industrial or operational systems using sensors to collect data. The system processes this data to perform predictive analytics, which includes estimating the future operation of specific components within the monitored systems. These estimates help anticipate component behavior, performance degradation, or potential failures, enabling proactive maintenance and optimization. The system may analyze sensor data in real-time or near real-time, applying machine learning or statistical models to derive predictive insights. By distributing the analytics workload across multiple nodes or edge devices, the system improves scalability and reduces latency compared to centralized approaches. The predictive analytics may also incorporate historical data, environmental factors, or operational patterns to enhance accuracy. This capability is particularly useful in industries such as manufacturing, energy, or transportation, where component reliability directly impacts efficiency and safety. The system may integrate with existing monitoring infrastructure or operate as a standalone solution, providing actionable predictions to operators or automated control systems.
6. The distributed analytics system as recited in claim 5 , wherein said estimate is the remaining operational life of said component of said at least one monitored system.
A distributed analytics system monitors the operational health of industrial systems by analyzing sensor data from components such as machinery, equipment, or infrastructure. The system collects real-time data from sensors embedded in these components and processes the data using distributed computing techniques to detect anomalies, predict failures, and estimate the remaining operational life of each component. By leveraging machine learning algorithms and statistical models, the system identifies patterns indicative of degradation or impending failure, allowing for proactive maintenance. The system integrates data from multiple sources, including historical performance records and environmental conditions, to refine its predictions. The estimated remaining operational life is calculated based on the component's current state, historical wear trends, and operational stress factors. This enables operators to schedule maintenance before critical failures occur, reducing downtime and maintenance costs. The system may also prioritize components based on their criticality and failure risk, optimizing resource allocation. The distributed architecture ensures scalability and fault tolerance, allowing the system to handle large volumes of data from multiple systems simultaneously. The analytics are performed in real-time or near-real-time, providing timely insights for decision-making. The system may also generate alerts or recommendations for corrective actions, integrating with existing maintenance management systems.
7. The distributed analytics system as recited in claim 1 , wherein said prescriptive analytics are based on a threshold performance of a component of said at least one monitored system associated with said sensor.
A distributed analytics system monitors industrial systems using sensors to collect operational data. The system analyzes this data to identify performance trends and predict potential failures, enabling proactive maintenance. A key feature is the use of prescriptive analytics, which not only predicts issues but also recommends corrective actions. These prescriptive analytics are based on predefined performance thresholds for individual system components. When a component's performance deviates from the threshold, the system generates actionable insights, such as maintenance schedules or adjustments, to optimize system efficiency and reduce downtime. The system integrates data from multiple sensors across different components, ensuring comprehensive monitoring and accurate analytics. By leveraging distributed computing, the system processes large datasets in real-time, providing timely recommendations to improve operational reliability. The focus on component-specific thresholds ensures precise and relevant prescriptive actions, tailored to the unique requirements of each monitored system. This approach enhances decision-making for maintenance teams and system operators, leading to cost savings and improved performance.
8. The distributed analytics system as recited in claim 1 , wherein said architect subsystem is remote from said edge subsystem.
A distributed analytics system processes data across multiple locations to improve efficiency and reduce latency. The system includes an edge subsystem that collects and processes data at the source, such as from IoT devices or sensors, and an architect subsystem that manages and coordinates analytics tasks. The edge subsystem performs initial data filtering, aggregation, and preprocessing to reduce the volume of data transmitted to the architect subsystem. The architect subsystem handles more complex analytics, such as machine learning or statistical analysis, and distributes tasks to the edge subsystem as needed. By separating these functions, the system minimizes data transfer delays and optimizes computational resources. The edge subsystem operates locally, while the architect subsystem is physically remote, allowing for centralized management of distributed analytics tasks. This architecture ensures real-time processing at the edge while leveraging cloud or centralized computing for advanced analytics. The system is designed for applications requiring low-latency decision-making, such as industrial automation, smart cities, or healthcare monitoring.
9. The distributed analytics system recited in claim 1 , wherein said architect subsystem aggregates the information received from a plurality of edge processing devices to modify the analytic models and redeploy to one or more of said edge processing devices.
A distributed analytics system processes data at edge devices, which are computing nodes located close to data sources. These edge devices perform local analytics using pre-trained models to reduce latency and bandwidth usage. However, as data patterns evolve, the models may become outdated, leading to reduced accuracy and performance. The system addresses this by including an architect subsystem that continuously collects and aggregates information from multiple edge devices. This aggregated data is used to update and refine the analytic models. Once updated, the improved models are redeployed to one or more edge devices, ensuring they remain accurate and effective over time. The system dynamically adapts to changing data conditions, maintaining high-quality analytics at the edge. This approach minimizes the need for centralized processing while keeping models optimized for real-time decision-making.
10. A method in a distributed analytics system to control the operation of a plurality of monitored systems, said distributed analytics system comprising an architect subsystem and an edge subsystem, said edge subsystem comprising a plurality of edge processing devices located proximate to said plurality of monitored systems, said method comprising the steps of: deploying, from said architect subsystem, analytic models to said edge processing devices based on sensor characteristics of said monitored systems; and, receiving, at each of said edge processing devices, at least one of said analytic models, each of said edge processing devices operative to: 1) independently perform predictive and prescriptive analytics on sensor data from at least one monitored system, wherein said prescriptive analytics includes a future action on a component of said monitored system associated with said sensor; 2) provide control signals to said at least one monitored system according to said predictive and prescriptive analytics; and, 3) periodically send information to said architect subsystem, including monitored system responses to said control signals, whereby said architect subsystem can modify said analytic models to improve system performance of said monitored systems.
The invention relates to a distributed analytics system for controlling monitored systems, such as industrial equipment or machinery, by leveraging edge computing and centralized model management. The system addresses the challenge of efficiently processing sensor data from multiple monitored systems in real-time while optimizing performance through adaptive analytics. The system includes an architect subsystem and an edge subsystem. The edge subsystem consists of multiple edge processing devices deployed near the monitored systems to minimize latency. The architect subsystem deploys analytic models to these edge devices based on the sensor characteristics of the monitored systems. Each edge device independently performs predictive and prescriptive analytics on sensor data, where prescriptive analytics determines future actions for system components. The edge devices then send control signals to the monitored systems based on these analytics. Additionally, the edge devices periodically transmit performance data, including system responses to control signals, back to the architect subsystem. The architect subsystem uses this feedback to refine and update the analytic models, improving overall system performance over time. This approach enables real-time decision-making at the edge while allowing centralized optimization of analytics models.
11. The method as recited in claim 10 , wherein performing said predictive and prescriptive analytics is on at least a component of said at least one monitored system based on said sensor data.
This invention relates to predictive and prescriptive analytics for monitored systems, particularly in industrial or operational environments where sensor data is collected. The problem addressed is the need to analyze sensor data to predict system behavior and prescribe corrective actions, improving efficiency and reducing downtime. The method involves monitoring at least one system using sensors to collect data, then performing predictive and prescriptive analytics on at least one component of the monitored system based on the sensor data. Predictive analytics involves forecasting future system states or failures, while prescriptive analytics recommends actions to optimize performance or prevent issues. The analytics may be applied to individual components or the entire system, depending on the data and requirements. The method may also include generating alerts or control signals based on the analytics results, enabling automated or manual intervention. The approach enhances decision-making by leveraging real-time or historical sensor data to improve system reliability and operational efficiency.
12. The method as recited in claim 10 , wherein said information includes a current status of a component of said at least one monitored system associated with said sensor.
This invention relates to monitoring systems, particularly for tracking the status of components within industrial or automated systems. The problem addressed is the need for real-time or near-real-time monitoring of system components to ensure operational efficiency, detect failures, and enable predictive maintenance. The invention provides a method for collecting and analyzing sensor data from monitored systems, where the data includes the current status of individual components. The method involves deploying sensors to gather information about system performance, processing this data to determine the operational state of components, and transmitting the results to a central monitoring system. The status information may include operational metrics such as temperature, pressure, vibration, or other relevant parameters, allowing for continuous assessment of component health. By integrating this data, the system can identify anomalies, predict potential failures, and trigger maintenance actions before critical issues arise. The method enhances system reliability and reduces downtime by providing actionable insights into component conditions. This approach is particularly useful in industrial automation, manufacturing, and infrastructure management, where component performance directly impacts overall system efficiency.
13. The method as recited in claim 10 , wherein said information includes a characteristic of said at least one monitored system based on said sensor data from a plurality of sensors.
This invention relates to monitoring and analyzing systems using sensor data to derive characteristics of the monitored systems. The method involves collecting sensor data from multiple sensors deployed across a system or environment. The collected data is processed to identify and extract relevant characteristics of the monitored system, such as performance metrics, operational states, or environmental conditions. These characteristics are then used to assess the system's behavior, detect anomalies, or optimize performance. The method may involve real-time or batch processing of sensor data, depending on the application. By leveraging data from multiple sensors, the system can provide a comprehensive and accurate representation of the monitored system's state, enabling better decision-making and predictive maintenance. The approach is applicable in various domains, including industrial automation, healthcare monitoring, and environmental sensing, where understanding system characteristics from sensor inputs is critical for efficient operation and reliability.
14. The method as recited in claim 10 , wherein said predictive analytics includes an estimate of an operation of a component of said at least one monitored system associated with said sensor.
This invention relates to predictive analytics for monitoring and maintaining industrial systems. The technology addresses the challenge of anticipating component failures or performance degradation in complex systems by analyzing sensor data to estimate future operational states. The method involves collecting sensor data from at least one monitored system, where the sensors measure parameters such as temperature, pressure, or vibration. The data is processed to identify patterns or anomalies that indicate potential issues. The predictive analytics component then estimates the future operation of specific system components, such as a motor, pump, or valve, based on historical and real-time data trends. This allows for proactive maintenance, reducing downtime and repair costs. The system may also include a user interface to display predictions, alerts, or recommended actions. The method can be applied to various industrial systems, including manufacturing equipment, power plants, or transportation infrastructure, where component reliability is critical. The invention improves upon existing monitoring systems by providing component-specific predictions rather than general system health assessments.
15. The method as recited in claim 14 , wherein said estimate is the remaining operational life of said component of said at least one monitored system.
This invention relates to predictive maintenance in industrial systems, specifically estimating the remaining operational life of monitored components. The method involves analyzing sensor data from at least one monitored system to detect anomalies or deviations from expected performance. The system includes sensors that collect operational data, a data processing unit that analyzes the data to identify patterns or trends, and a predictive model that estimates the remaining operational life of the component based on the analyzed data. The method may also involve comparing the estimated remaining life to a predefined threshold to determine if maintenance is required. The predictive model can be updated over time as new data is collected, improving accuracy. The system may also include a user interface to display the estimated remaining life and maintenance recommendations. The invention aims to reduce unplanned downtime and maintenance costs by providing early warnings of potential component failures. The method can be applied to various industrial systems, including machinery, vehicles, and infrastructure, where component degradation over time is a concern. The system may also incorporate historical data from similar components to refine the predictive model. The invention focuses on continuous monitoring and real-time analysis to provide actionable insights for maintenance planning.
16. The method as recited in claim 10 , wherein said prescriptive analytics are based on a threshold performance of a component of said at least one monitored system associated with said sensor.
This invention relates to prescriptive analytics for system monitoring and optimization. The technology addresses the challenge of improving system performance by analyzing sensor data to identify underperforming components and recommending corrective actions. The method involves monitoring at least one system using sensors to collect performance data from various components. A performance threshold is established for each component, and the system compares the collected data against these thresholds to detect deviations. When a component's performance falls below the threshold, the system generates prescriptive analytics, which include recommendations for adjustments or interventions to restore optimal performance. These recommendations may involve adjusting operational parameters, scheduling maintenance, or replacing parts. The method ensures continuous monitoring and adaptive responses to maintain system efficiency and reliability. By leveraging real-time data and predefined thresholds, the system automates decision-making to minimize downtime and enhance overall system functionality. The invention is particularly useful in industrial, manufacturing, or infrastructure applications where component performance directly impacts operational outcomes.
17. The method as recited in claim 10 , wherein said architect subsystem is remote from said edge subsystem.
A system and method for distributed computing involves an architecture where processing tasks are dynamically allocated between a central architect subsystem and one or more edge subsystems. The architect subsystem manages workload distribution, resource allocation, and coordination of tasks across the edge subsystems, which are responsible for executing the assigned tasks. The edge subsystems may be geographically dispersed and operate with varying levels of connectivity. The system optimizes performance by balancing computational load, minimizing latency, and ensuring efficient use of available resources. In some configurations, the architect subsystem is physically or logically separated from the edge subsystems, allowing for centralized control while maintaining distributed execution. This separation enables scalability, fault tolerance, and adaptability to changing network conditions. The system is particularly useful in environments where real-time processing, low-latency responses, or localized data handling are required, such as in IoT networks, edge computing, or decentralized applications. The method ensures seamless coordination between the architect and edge subsystems, even under intermittent connectivity, by implementing adaptive synchronization and task prioritization mechanisms. The overall approach enhances efficiency, reliability, and responsiveness in distributed computing environments.
18. The method recited in claim 10 , further comprising the steps of said architect subsystem aggregating the information received from a plurality of edge processing devices to modify the analytic models and redeploy to one or more of said edge processing devices.
This invention relates to distributed computing systems, specifically methods for managing and optimizing analytic models across multiple edge processing devices. The problem addressed is the inefficiency of static analytic models in edge computing environments, where data characteristics and processing demands can vary significantly over time. The solution involves a dynamic system that continuously improves and redeploys analytic models to edge devices based on aggregated data from the network. The system includes an architect subsystem that collects and analyzes information from multiple edge processing devices. These devices perform local data processing tasks using deployed analytic models. The architect subsystem aggregates the performance data, usage patterns, and other relevant information from the devices to identify opportunities for model optimization. Based on this analysis, the subsystem modifies the analytic models to improve accuracy, efficiency, or other performance metrics. The updated models are then redeployed to one or more edge processing devices, ensuring that the system adapts to changing conditions. This closed-loop process enables continuous improvement of the analytic models without manual intervention, enhancing the overall performance and adaptability of the edge computing network.
Unknown
October 6, 2020
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.